Please note that diffs are not public domain; they are subject to the copyright notices on the relevant files. =================================================================== RCS file: /ftp/cvs/cvsroot/src/sys/netinet/ip_input.c,v rcsdiff: /ftp/cvs/cvsroot/src/sys/netinet/ip_input.c,v: warning: Unknown phrases like `commitid ...;' are present. retrieving revision 1.50 retrieving revision 1.68 diff -u -p -r1.50 -r1.68 --- src/sys/netinet/ip_input.c 1997/06/24 02:26:04 1.50 +++ src/sys/netinet/ip_input.c 1998/07/17 00:28:00 1.68 @@ -1,4 +1,41 @@ -/* $NetBSD: ip_input.c,v 1.50 1997/06/24 02:26:04 thorpej Exp $ */ +/* $NetBSD: ip_input.c,v 1.68 1998/07/17 00:28:00 sommerfe Exp $ */ + +/*- + * Copyright (c) 1998 The NetBSD Foundation, Inc. + * All rights reserved. + * + * This code is derived from software contributed to The NetBSD Foundation + * by Public Access Networks Corporation ("Panix"). It was developed under + * contract to Panix by Eric Haszlakiewicz and Thor Lancelot Simon. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the NetBSD + * Foundation, Inc. and its contributors. + * 4. Neither the name of The NetBSD Foundation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. AND CONTRIBUTORS + * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED + * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR + * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE FOUNDATION OR CONTRIBUTORS + * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ /* * Copyright (c) 1982, 1986, 1988, 1993 @@ -35,6 +72,9 @@ * @(#)ip_input.c 8.2 (Berkeley) 1/4/94 */ +#include "opt_gateway.h" +#include "opt_mrouting.h" + #include #include #include @@ -64,9 +104,6 @@ #include #include -/* XXX should really put this in libkern.h */ -#define offsetof(type, member) ((size_t)(&((type *)0)->member)) - #ifndef IPFORWARDING #ifdef GATEWAY #define IPFORWARDING 1 /* forward IP packets not for us */ @@ -83,6 +120,13 @@ #ifndef IPALLOWSRCRT #define IPALLOWSRCRT 1 /* allow source-routed packets */ #endif +#ifndef IPMTUDISC +#define IPMTUDISC 0 +#endif +#ifndef IPMTUDISCTIMEOUT +#define IPMTUDISCTIMEOUT (10 * 60) /* as per RFC 1191 */ +#endif + /* * Note: DIRECTED_BROADCAST is handled this way so that previous * configuration using this option will Just Work. @@ -100,16 +144,25 @@ int ip_defttl = IPDEFTTL; int ip_forwsrcrt = IPFORWSRCRT; int ip_directedbcast = IPDIRECTEDBCAST; int ip_allowsrcrt = IPALLOWSRCRT; +int ip_mtudisc = IPMTUDISC; +u_int ip_mtudisc_timeout = IPMTUDISCTIMEOUT; #ifdef DIAGNOSTIC int ipprintfs = 0; #endif +struct rttimer_queue *ip_mtudisc_timeout_q = NULL; + extern struct domain inetdomain; extern struct protosw inetsw[]; u_char ip_protox[IPPROTO_MAX]; int ipqmaxlen = IFQ_MAXLEN; struct in_ifaddrhead in_ifaddr; +struct in_ifaddrhashhead *in_ifaddrhashtbl; struct ifqueue ipintrq; +struct ipstat ipstat; +u_int16_t ip_id; +int ip_defttl; +struct ipqhead ipq; /* * We need to save the IP options in case a protocol wants to respond @@ -152,6 +205,11 @@ ip_init() ip_id = time.tv_sec & 0xffff; ipintrq.ifq_maxlen = ipqmaxlen; TAILQ_INIT(&in_ifaddr); + in_ifaddrhashtbl = + hashinit(IN_IFADDR_HASH_SIZE, M_IFADDR, M_WAITOK, &in_ifaddrhash); + if (ip_mtudisc != 0) + ip_mtudisc_timeout_q = + rt_timer_queue_create(ip_mtudisc_timeout); } struct sockaddr_in ipaddr = { sizeof(ipaddr), AF_INET }; @@ -168,6 +226,7 @@ ipintr() register struct mbuf *m; register struct ipq *fp; register struct in_ifaddr *ia; + register struct ifaddr *ifa; struct ipqent *ipqe; int hlen = 0, mff, len, s; #ifdef PFIL_HOOKS @@ -250,17 +309,30 @@ next: m_adj(m, len - m->m_pkthdr.len); } + /* + * Assume that we can create a fast-forward IP flow entry + * based on this packet. + */ + m->m_flags |= M_CANFASTFWD; + #ifdef PFIL_HOOKS /* - * Run through list of hooks for input packets. + * Run through list of hooks for input packets. If there are any + * filters which require that additional packets in the flow are + * not fast-forwarded, they must clear the M_CANFASTFWD flag. + * Note that filters must _never_ set this flag, as another filter + * in the list may have previously cleared it. */ m0 = m; - for (pfh = pfil_hook_get(PFIL_IN); pfh; pfh = pfh->pfil_link.le_next) + for (pfh = pfil_hook_get(PFIL_IN); pfh; pfh = pfh->pfil_link.tqe_next) if (pfh->pfil_func) { rv = pfh->pfil_func(ip, hlen, m->m_pkthdr.rcvif, 0, &m0); if (rv) goto next; - ip = mtod(m = m0, struct ip *); + m = m0; + if (m == NULL) + goto next; + ip = mtod(m, struct ip *); } #endif /* PFIL_HOOKS */ @@ -277,12 +349,13 @@ next: /* * Check our list of addresses, to see if the packet is for us. */ - for (ia = in_ifaddr.tqh_first; ia; ia = ia->ia_list.tqe_next) { - if (in_hosteq(ip->ip_dst, ia->ia_addr.sin_addr)) - goto ours; - if (((ip_directedbcast == 0) || (ip_directedbcast && - ia->ia_ifp == m->m_pkthdr.rcvif)) && - (ia->ia_ifp->if_flags & IFF_BROADCAST)) { + INADDR_TO_IA(ip->ip_dst, ia); + if (ia != NULL) goto ours; + if (m->m_pkthdr.rcvif->if_flags & IFF_BROADCAST) { + for (ifa = m->m_pkthdr.rcvif->if_addrlist.tqh_first; + ifa != NULL; ifa = ifa->ifa_list.tqe_next) { + if (ifa->ifa_addr->sa_family != AF_INET) continue; + ia = ifatoia(ifa); if (in_hosteq(ip->ip_dst, ia->ia_broadaddr.sin_addr) || in_hosteq(ip->ip_dst, ia->ia_netbroadcast) || /* @@ -292,6 +365,12 @@ next: ip->ip_dst.s_addr == ia->ia_subnet || ip->ip_dst.s_addr == ia->ia_net) goto ours; + /* + * An interface with IP address zero accepts + * all packets that arrive on that interface. + */ + if (in_nullhost(ia->ia_addr.sin_addr)) + goto ours; } } if (IN_MULTICAST(ip->ip_dst.s_addr)) { @@ -643,6 +722,9 @@ ip_slowtimo() ip_freef(fp); } } +#ifdef GATEWAY + ipflow_slowtimo(); +#endif splx(s); } @@ -812,7 +894,7 @@ ip_dooptions(m) break; case IPOPT_TS_TSANDADDR: - if (ipt->ipt_ptr + sizeof(n_time) + + if (ipt->ipt_ptr - 1 + sizeof(n_time) + sizeof(struct in_addr) > ipt->ipt_len) goto bad; ipaddr.sin_addr = dst; @@ -826,7 +908,7 @@ ip_dooptions(m) break; case IPOPT_TS_PRESPEC: - if (ipt->ipt_ptr + sizeof(n_time) + + if (ipt->ipt_ptr - 1 + sizeof(n_time) + sizeof(struct in_addr) > ipt->ipt_len) goto bad; bcopy((caddr_t)sin, (caddr_t)&ipaddr.sin_addr, @@ -1126,8 +1208,13 @@ ip_forward(m, srcrt) if (type) ipstat.ips_redirectsent++; else { - if (mcopy) + if (mcopy) { +#ifdef GATEWAY + if (mcopy->m_flags & M_CANFASTFWD) + ipflow_create(&ipforward_rt, mcopy); +#endif m_freem(mcopy); + } return; } } @@ -1235,6 +1322,10 @@ ip_sysctl(name, namelen, oldp, oldlenp, void *newp; size_t newlen; { + extern int subnetsarelocal; + + int error, old; + /* All sysctl names at this level are terminal. */ if (namelen != 1) return (ENOTDIR); @@ -1265,6 +1356,64 @@ ip_sysctl(name, namelen, oldp, oldlenp, case IPCTL_ALLOWSRCRT: return (sysctl_int(oldp, oldlenp, newp, newlen, &ip_allowsrcrt)); + case IPCTL_SUBNETSARELOCAL: + return (sysctl_int(oldp, oldlenp, newp, newlen, + &subnetsarelocal)); + case IPCTL_MTUDISC: + error = sysctl_int(oldp, oldlenp, newp, newlen, + &ip_mtudisc); + if (ip_mtudisc != 0 && ip_mtudisc_timeout_q == NULL) { + ip_mtudisc_timeout_q = + rt_timer_queue_create(ip_mtudisc_timeout); + } else if (ip_mtudisc == 0 && ip_mtudisc_timeout_q != NULL) { + rt_timer_queue_destroy(ip_mtudisc_timeout_q, TRUE); + ip_mtudisc_timeout_q = NULL; + } + return error; + case IPCTL_ANONPORTMIN: + old = anonportmin; + error = sysctl_int(oldp, oldlenp, newp, newlen, &anonportmin); + if (anonportmin >= anonportmax || anonportmin > 65535 +#ifndef IPNOPRIVPORTS + || anonportmin < IPPORT_RESERVED +#endif + ) { + anonportmin = old; + return (EINVAL); + } + return (error); + case IPCTL_ANONPORTMAX: + old = anonportmax; + error = sysctl_int(oldp, oldlenp, newp, newlen, &anonportmax); + if (anonportmin >= anonportmax || anonportmax > 65535 +#ifndef IPNOPRIVPORTS + || anonportmax < IPPORT_RESERVED +#endif + ) { + anonportmax = old; + return (EINVAL); + } + return (error); + case IPCTL_MTUDISCTIMEOUT: + error = sysctl_int(oldp, oldlenp, newp, newlen, + &ip_mtudisc_timeout); + if (ip_mtudisc_timeout_q != NULL) + rt_timer_queue_change(ip_mtudisc_timeout_q, + ip_mtudisc_timeout); + return (error); +#ifdef GATEWAY + case IPCTL_MAXFLOWS: + { + int s; + + error = sysctl_int(oldp, oldlenp, newp, newlen, + &ip_maxflows); + s = splsoftnet(); + ipflow_reap(0); + splx(s); + return (error); + } +#endif default: return (EOPNOTSUPP); }